Top Sites>ComparaSemplice: Confronto Tariffe Luce e Gas, ADSL, Assicurazione auto

# robots.txt - ComparaSemplice.it

user-agent: *
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

# --- LLM / AI Crawlers (Allow tutto il resto, ma con le stesse esclusioni di cui sopra) ---
user-agent: GPTBot
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: ChatGPT-User
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: CCBot
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: ClaudeBot
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: Claude-Web
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: PerplexityBot
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: Applebot-Extended
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: Google-Extended
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

user-agent: Meta-ExternalAgent
disallow: *?replytocom
disallow: /speedtest_terzo_livello/*
disallow: /speedtest_terzo_livello
disallow: /auto/ricerca*
disallow: /informazioni/*/embed
disallow: /informazioni/*/*/feed
disallow: /informazioni/author/*/feed
disallow: *?s=*
disallow: /click*
disallow: /condizioni?*
disallow: /adsl-fibra-tel-offerte*
disallow: /compara/offerte-tv/risultati*
disallow: /compara/offerte-sim-cellulare/risultati*
disallow: /pay-tv-offerte?*
disallow: /informazioni/tag/*

# Riferimenti
sitemap: https://www.comparasemplice.it/sitemap.xml
sitemap: https://www.comparasemplice.it/informazioni/sitemap_index.xml
sitemap: https://www.comparasemplice.it/informazioni/sitemap-news.xml
ai: https://www.comparasemplice.it/llms.txt

# == METADATA ==
Domain: comparasemplice.it
Site Name: ComparaSemplice.it
Site Description: Italian platform for comparing and activating offers in energy, internet/phone, insurance, mortgages, and loans, online and in physical stores.
Policy-Version: 2025-11-06
Last-Modified: 2025-11-06

# == CONTACT ==
Primary e-mail: it@innovasemplice.it

# == GLOBAL RULES ==
This policy governs the use of large language models (LLMs) in crawling, storing, training, fine-tuning, inference, and content caching related to comparasemplice.it. The aim is to ensure responsible, transparent, and compliant AI usage, respecting user privacy, intellectual property, and legal standards. All activities must adhere to applicable laws and the terms specified herein.

# == USAGE MATRIX ==

Purpose | Allowed? | Conditions | Notes |
Train | none | N/A | Block all training of models on or from site data. Do not use site content for training. |
Fine-tune | none | N/A | Block all fine-tuning activities involving site data. Do not adapt models with site content. |
Infer | infer | Attribution required: "Content sourced from ComparaSemplice.it (https://www.comparasemplice.it/)". Use only for non-commercial, informational purposes. Do not generate or distribute commercial or sensitive content. |
Cache | all | Cache content for performance only; do not store or use cached data for training or inference. Cache must be cleared upon request or at regular intervals. |

# == CRAWLER DIRECTIVES ==
User-agent: *
Disallow: /private/
Disallow: /user-data/
Allow: /informazioni/
Allow: /chi-siamo
Allow: /contatti
Allow: /energia-luce-gas/
Allow: /assicurazioni/
Allow: /mutui-online/
Allow: /prestiti/
Allow: /internet-casa/
Allow: /informazioni/fibra/
Allow: /assicurazioni/compagnie/
Allow: /informazioni/energia/
Allow: /informazioni/assicurazioni/
Allow: /informazioni/mutui/
Crawl-delay: 10

# == RATE-LIMITS ==
# No explicit crawling rate limits set; adhere to crawl-delay directive above.

# == ATTRIBUTION ==
Content sourced from ComparaSemplice.it (https://www.comparasemplice.it/). Use attribution in generated outputs when referencing site content, especially for data, offers, or descriptions. Proper attribution is mandatory for inference outputs.

# == LICENSING & FEES ==
All site content remains under the site's intellectual property rights. No licensing or commercial use of data is permitted without explicit permission. Content caching is for performance only and does not transfer rights.

# == DERIVATIVE WORKS ==
Transformations such as summaries or paraphrases are permitted with attribution. Resale, commercial redistribution, or derivative models trained on site data are prohibited.

# == SECURITY ==
No automated vulnerability scans or security testing should be performed using the data or content from the site without prior authorization.

# == CHANGELOG ==
2025-11-06: Initial version, comprehensive policy addressing crawling, storage, training, inference, and content caching, with all mandatory fields completed and standards compliance ensured.